How to Use the Lanhu MCP in Mastra AI

Q: Can I build a multi-step design sync with Mastra AI and Lanhu?

Yes, you can chain listboards to find updated layouts, then call listlayers to inspect changed Lanhu components. Mastra AI manages this state across execution steps to ensure your code generation tools only run when actual design changes occur.

Q: How do I configure the Lanhu MCP Server inside a Mastra AI agent?

Instantiate the Lanhu MCP Server using the MCPClient class and register it in your Mastra AI agent's tools array. The agent then dynamically decides when to run getfile based on user prompts.

Q: Can we require human approval before applying Lanhu changes in Mastra AI?

Yes, you can set requireToolApproval on critical actions like modifying local files based on Lanhu data. This stops the Mastra AI workflow until a developer reviews the proposed asset updates.

Automate design handoffs and sync workflows with the Mastra AI agent framework and the Lanhu MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lanhu MCP to Mastra AI

Create your Vinkius account to connect Lanhu to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Lanhu with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger Mastra AI code generation from Lanhu assets

`list_project_files` identifies new design uploads in Lanhu to kick off your Mastra AI automated handoff pipeline. If a file is updated, the Mastra AI agent triggers a sequence to pull the asset and generate code. The Mastra AI workflow uses `get_file` to download the Lanhu asset binary, then runs conditional checks to verify file size. Should the download fail, Mastra's built-in retry engine attempts the fetch again before alerting the team.

Route Lanhu feedback using this MCP Server

`get_comments` extracts unresolved notes from Lanhu design boards so your Mastra AI agent can route them to the correct developer. This MCP Server handles the connection to ensure no feedback is lost. The Mastra AI agent uses `list_members` to match the Lanhu comment author with your internal team directory. By automating this, you bypass manual design-to-engineering handoffs entirely.

Audit Lanhu design systems with Mastra AI

`list_layers` exposes the full Lanhu document structure, allowing your Mastra AI agent to inspect layer naming conventions. It flags non-standard names directly in your pull requests. By calling `list_team_projects` and tracking changes across Lanhu boards, the Mastra AI agent builds an automated compliance report. This ensures your design system stays clean across all teams.

Setup guide

Set up Lanhu MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Lanhu tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "lanhu-mcp-client",
  servers: {
    "lanhu-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Lanhu Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Lanhu tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Lanhu transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Lanhu. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Lanhu now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Lanhu MCP in Mastra AI

Mastra AI uses its built-in workflow engine to queue requests and execute automatic retries with exponential backoff. If `get_project` hits a limit, the Mastra AI agent pauses and retries without breaking your Lanhu pipeline.

Yes, you can chain `list_boards` to find updated layouts, then call `list_layers` to inspect changed Lanhu components. Mastra AI manages this state across execution steps to ensure your code generation tools only run when actual design changes occur.

Instantiate the Lanhu MCP Server using the `MCPClient` class and register it in your Mastra AI agent's tools array. The agent then dynamically decides when to run `get_file` based on user prompts.

Yes, you can set `requireToolApproval` on critical actions like modifying local files based on Lanhu data. This stops the Mastra AI workflow until a developer reviews the proposed asset updates.

Your Lanhu workspace project metadata, comment threads, and layer hierarchies are processed in memory and never stored. The MCP Server architecture runs inside a V8 sandbox to ensure that design assets stay isolated during the Mastra AI workflow run.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript